StofNet: Super-resolution Time of Flight Network
This work addresses depth sensing problems for robotics, medical imaging, and non-destructive testing, presenting an incremental improvement through a tailored architecture.
The paper tackles the challenge of reliable and accurate Time of Flight (ToF) depth sensing in complex ambient conditions by proposing StofNet, a super-resolution network that achieves superior performance in precision, reliability, and model complexity compared to six state-of-the-art methods on two datasets.
Time of Flight (ToF) is a prevalent depth sensing technology in the fields of robotics, medical imaging, and non-destructive testing. Yet, ToF sensing faces challenges from complex ambient conditions making an inverse modelling from the sparse temporal information intractable. This paper highlights the potential of modern super-resolution techniques to learn varying surroundings for a reliable and accurate ToF detection. Unlike existing models, we tailor an architecture for sub-sample precise semi-global signal localization by combining super-resolution with an efficient residual contraction block to balance between fine signal details and large scale contextual information. We consolidate research on ToF by conducting a benchmark comparison against six state-of-the-art methods for which we employ two publicly available datasets. This includes the release of our SToF-Chirp dataset captured by an airborne ultrasound transducer. Results showcase the superior performance of our proposed StofNet in terms of precision, reliability and model complexity. Our code is available at https://github.com/hahnec/stofnet.